Management Of Brain Tumors Research Articles

Intraoperative Imaging and Optical Visualization Techniques for Brain Tumor Resection: A Narrative Review.

Advancements in intraoperative visualization and imaging techniques are increasingly central to the success and safety of brain tumor surgery, leading to transformative improvements in patient outcomes. This comprehensive review intricately describes the evolution of conventional and emerging technologies for intraoperative imaging, encompassing the surgical microscope, exoscope, Raman spectroscopy, confocal microscopy, fluorescence-guided surgery, intraoperative ultrasound, magnetic resonance imaging, and computed tomography. We detail how each of these imaging modalities contributes uniquely to the precision, safety, and efficacy of neurosurgical procedures. Despite their substantial benefits, these technologies share common challenges, including difficulties in image interpretation and steep learning curves. Looking forward, innovations in this field are poised to incorporate artificial intelligence, integrated multimodal imaging approaches, and augmented and virtual reality technologies. This rapidly evolving landscape represents fertile ground for future research and technological development, aiming to further elevate surgical precision, safety, and, most critically, patient outcomes in the management of brain tumors.

Automated Detection, Segmentation, and Tracking of Brain Metastases in Repeated Courses of Stereotactic Radiosurgery Using Integrated Artificial Intelligence.

Salvage stereotactic radiosurgery (SRS) for distant brain metastases has been demonstrated as a safe and effective approach for intracranial recurrences after initial SRS. However, accurate tumor detection and segmentation among responding tumors within the irradiated parenchyma can be challenging. The requirement for the registration and reference to the previous course of SRS is very time-consuming and suffers significant inter and intra-reader variability. Artificial intelligence (AI)-assisted system has been proven to improve the accuracy and efficiency in the clinical flow of de-novo SRS. We hypothesize that an integrated AI system can facilitate an automated tumor contouring process for repeated SRS. Three patients who underwent their third course of SRS to brain metastases were selected for the pioneering works. They have had two sessions of SRS with a mean lesion number of 4 and 3.7, respectively. VBrain, an FDA-approved brain tumor management AI platform, was used to co-registered serial MR scans and automatically identify, track, and contour brain metastases for each course of SRS. The AI also indicated new lesions and treated lesions for each course. Three radiation oncologists experienced in brain SRS contoured the gross tumor volumes (GTVs) of the third course of SRS in two reader modes (assisted then unassisted) with a memory washout period of one week between each section. The segmentation ground truth was established through consensus among the three experts. Lesion-wise sensitivity, contouring accuracy, and consuming time were compared between the two contouring modes. In each patient, there were 15, 11, and 9 metastases, with a median diameter of 4.72 (95% CI: 4.05, 6.91) mm. The mean lesion-wise sensitivity was 96.96±2.47% with AI assistance and 76.90 ± 7.10% without assistance. There were two false-positive lesions in the assisted read, resulting in a low average false-positive rate of 0.67 per patient, while no false positive for the unassisted mode. AI assistance improved contouring accuracy. The median Dice similarity coefficient (DSC) was 0.71 (95% CI: 0.55, 0.87) for assisted contouring and 0.65 (95% CI: 0.46, 0.85) for unassisted contouring. We also use average Hausdorff distance (HD) to measure segmentation results. The mean HD was 0.72± 0.13 mm versus 0.73±0.08 mm for the two contouring modes (p = 0.02) Furthermore, the median contouring time per case was significantly shorter with AI assistance than without assistance (20.8 minutes vs. 29.8 minutes; p < 0.001), corresponding to a 43.2% time-saving. Our results suggest that the integration of an AI-based system into repeated brain SRS can significantly improve the accuracy and efficiency of tumor detection and segmentation. This approach has the potential to streamline the treatment planning process for salvage SRS.

Quantitative Analysis of BrainAge using Neuroimaging Data to Estimate Radiation-Induced Brain Aging and Associations with Cognitive Changes in Brain Metastases Patients

Radiotherapy is critical in brain tumor management yet causes accelerated aging via irreparable damage to white matter, cortex, and subcortical areas. BrainAGE is an open-source machine learning tool that analyses morphology from raw quantitative structural MRI to generate a predictive 'BrainAge' value, enabling analyses of patients with neurodegenerative diseases. We assessed the utility of this algorithm in measuring brain age morphology in brain metastases patients on a clinical trial, analyzed differences in BrainAge and chronological age, and explored associations with cognitive performance. We analyzed pre-SRS high-resolution T1-weighted noncontrast volumetric MRI in patients with brain metastases (n = 57, median age 63 years, range 20-87) treated on a prospective clinical trial of cognitive-sparing SRS. The BrainAGE machine learning tool processed images to derive a BrainAge; it reliably generates this value using a Gaussian Processes regression, with a robust neurotypical training cohort. We examined correlations between BrainAge and chronological age with regression. Brain-predicted age gap (Brain-Gap) was calculated, defined as the difference between a patient's BrainAge and chronological age. We assessed cognitive function at baseline pre-SRS with a comprehensive battery of validated tests across multiple domains performed by a neuropsychologist, including memory (HVLT total), executive function (COWAT category fluency), and language (COWAT letter fluency). Raw test scores were scaled to T-scores adjusting for age, sex, and education level per testing norms. We examined if Brain-Gap was associated with cognitive performance pre-SRS. BrainAGE software was robust, estimating a BrainAge for all input MRI sequences. We found a strong correlation between BrainAge and chronological age (r-squared = 0.82). The Brain-Gap median value was 0.84 and the mean was -0.90, in years (range -18.30-11.36 years). Brain-Gap was not significantly associated with cognitive performance across the three tests at the pre-SRS timepoint. Among patients with impaired cognition (T<35), there was no significant difference in BrainAge relative to chronological age. To our knowledge, this is the first study utilizing the BrainAGE model as a biomarker of neuroanatomical age for brain tumors patients. Existing publications had lesion-free cohorts. Our results show that BrainAge was reliably associated with chronologic age in brain metastases patients pre-SRS. The Brain-Gap difference was minimal at baseline, and we found no significant association with pre-SRS cognitive performance. Future studies will examine this biomarker after SRS to look for individual aging radiation effects and prediction for cognitive changes after therapy.

Nanotube breakthroughs: unveiling the potential of carbon nanotubes as a dual therapeutic arsenal for Alzheimer's disease and brain tumors.

Alzheimer's disease (AD) and brain tumors are debilitating neurological conditions that pose significant challenges in current medical practices. Existing treatment options for AD primarily focus on symptom management, and brain tumors often require aggressive therapeutic approaches. Novel disease-modifying strategies and therapeutic agents are urgently needed to address the underlying causes of AD pathogenesis and improve brain tumor management. In recent years, nanoparticles (NPs) have shown promise as valuable tools in diagnosing and managing various brain disorders, including AD. Among these, carbon nanotubes (CNTs) have garnered attention for their unique properties and biomedical potential. Their ability to cross the blood-brain barrier (BBB) with ease opens up new possibilities for targeted drug delivery and neuroprotection. This literature review aims to explore the versatile nature of CNTs, which can be functionalized with various biomolecules or substances due to their sp2 hybridization. This adaptability enables them to specifically target cells and deliver medications under specific environmental conditions. Moreover, CNTs possess an exceptional capacity to penetrate cell membranes, making them valuable tools in the treatment of AD and brain tumors. By delving into the role of CNTs in biomedicine, this review sheds light on their potential in managing AD, offering a glimpse of hope for effective disease-modifying options. Understanding the mechanisms of CNTs' action and their capabilities in targeting and delivering medication to affected cells will pave the way for innovative therapeutic strategies that can improve the lives of those afflicted with these devastating neurological conditions. The exploration of CNTs as a dual therapeutic arsenal for both brain tumors and Alzheimer's disease holds great promise and may usher in a new era of effective treatment strategies for these challenging conditions.

Initial Experience of 18 F-FET PET-MR Image Fusion for Evaluation of Recurrent Primary Brain Tumors.

Background An accurate monitoring technique is crucial in brain tumors to choose the best treatment approach after surgery and/or chemoradiation. Radiological assessment of brain tumors is widely based on the magnetic resonance imaging (MRI) modality in this regard; however, MRI criteria are unable to precisely differentiate tumoral tissue from treatment-related changes. This study was conducted to evaluate whether fused MRI and O-(2- 18 F-fluoroethyl)-L-tyrosine ( 18 F-FET) positron emission tomography (PET) can improve the diagnostic accuracy of the practitioners to discriminate treatment-related changes from true recurrence of brain tumor. Methods We retrospectively analyzed 18 F-FET PET/computed tomography (CT) of 11 patients with histopathologically proven brain tumors that were suspicious for recurrence changes after 3 to 4 months of surgery. All the patients underwent MRI and 18 F-FET PET/CT. As a third assessment, fused 18 F-FET PET/MRI was also acquired. Finally, the diagnostic accuracy of the applied modalities was compared. Results Eleven patients aged 27 to 73 years with a mean age of 47 ± 13 years were enrolled. According to the results, 9/11 cases (82%) showed positive MRI and 6 cases (55%) showed positive PET/CT and PET/MRI. Tumoral recurrence was observed in six patients (55%) in the follow-up period. Based on the follow-up results, accuracy, sensitivity, specificity, positive predictive value (PPV), and negative predictive value (NPV) were 64, 85, 25, 67, and 50%, respectively, for MRI alone and 91, 85, 100, 100, and 80%, respectively, for both PET/CT and PET/MRI. Conclusion This study found that 18 F-FET PET-MR image fusion in the management of brain tumors might improve recurrence detection; however, further well-designed studies are needed to verify these preliminary data.

Seizure outcomes after resection of primary brain tumors in pediatric patients: a systematic review and meta-analysis.

Primary brain neoplasms are the most common solid tumors in pediatric patients and seizures are a common presenting symptom. Surgical intervention improves oncologic outcomes and seizure burden. A better understanding of factors that influence seizure outcomes in the surgical management of primary brain tumors of childhood can guide treatment approach thereby improving patient quality of life. We performed a systematic analysis using articles queried from PubMed, EMBASE, and Cochrane published from January 1990 to August 2022 to determine predictors of seizure outcomes in pediatric patients undergoing resection of primary brain tumors. We identified 24 retrospective cohort studies, one prospective cohort study, and one mixed retrospective and prospective study for the systematic analysis. A total of 831 pediatric patients were available for analysis. 668 (80.4%) patients achieved seizure freedom after surgery. Complete tumor resection increased the likelihood of a seizure-free (Engel I) outcome compared to subtotal resection (OR 7.1, 95% CI 2.3-21.9). Rates of Engel I seizure outcomes did not significantly differ based on factors such as age at seizure onset, duration of epilepsy, gender, tumor laterality, or age at surgery, but trended towards significance for improved outcomes in temporal lobe tumors. Primary brain tumors in the pediatric population are commonly associated with seizures. Resection of these lesions reduces seizure burden and is associated with high rates of seizure freedom. Complete resection, compared to subtotal resection, significantly increases the likelihood of seizure-free outcomes.

Cortical-Subcortical Functional Preservation and Rehabilitation in Neuro-Oncology: Tractography-MIPS-IONM-TMS Proof-of-Concept Study.

Surgical management of deep-seated brain tumors requires precise functional navigation and minimally invasive surgery. Preoperative mapping using navigated transcranial magnetic stimulation (nTMS), intraoperative neurophysiological monitoring (IONM), and minimally invasive parafascicular surgery (MIPS) act together in a functional-sparing approach. nTMS also provides a rehabilitation tool to maximize functional recovery. This is a single-center retrospective proof-of-concept cohort study between January 2022 and June 2023 of patients admitted for surgery with motor eloquent deep-seated brain tumors. The study enrolled seven adult patients, five females and two males, with a mean age of 56.28 years old. The lesions were located in the cingulate gyrus (three patients), the central core (two patients), and the basal ganglia (two patients). All patients had preoperative motor deficits. The most common histological diagnosis was metastasis (five patients). The MIPS approach to the mid-cingulate lesions involved a trajectory through the fronto-aslant tract (FAT) and the fronto-striatal tract (FST). No positive nTMS motor responses were resected as part of the outer corridor for MIPS. Direct cortical stimulation produced stable motor-evoked potentials during the surgeries with no warning signs. Gross total resection (GTR) was achieved in three patients and near-total resection (NTR) in four patients. Post-operatively, all patients had a deterioration of motor function with no ischemia in the postoperative imaging (cavity-to-CST distance 0-4 mm). After nTMS with low-frequency stimulation in the contralateral motor cortex, six patients recovered to their preoperative functional status and one patient improved to a better functional condition. A combined Tractography-MIPS-IONM-TMS approach provides a successful functional-sparing approach to deep-seated motor eloquent tumors and a rehabilitation framework for functional recovery after surgery.

The clinical impact of amino acid positron emission tomography measurements in the treatment of primary malignant brain tumors

Despite the large-scale diagnostic and therapeutic progress of recent years, the heterogeneity and therapeutic management of adult primary malignant brain tumors pose a significant challenge to the attending physician. Based on the research and experience accumulated over the past two decades, the range of patients who can benefit the most from complex oncology treatment has been outlined, and it has been confirmed that a reliable complex diagnostic background is essential for adequate therapeutic management. However, after some necessary therapeutic steps, the "gold standard" magnetic resonance imaging (MRI) is not always able to accurately assess and diagnose post-therapeutic conditions. Thanks to the collaboration of the nuclear medicine and neuro-oncology professions, more and more types of radiotracer compounds are now available in more and more centers, including amino acid ligands and thus, positron emission tomography (PET) examinations with the radiopharmaceutical O-(2-[18F]fluoroethyl)-L-tyrosine. The metabolic state, as a kind of fourth dimension of imaging, is an essential part of adequate modern diagnostics. Combining advanced MRI techniques and PET-based (PET/CT, PET/MRI) measurements with a suitable tracer can place therapeutic decisions on a reliable basis. We present the clinical significance of amino acid-PET-based hybrid nuclear medicine imaging studies in the therapeutic management of these patients by reviewing the literature data on the practice of the method in Hungary and abroad and presenting the results of our retrospective summary research so far. Orv Hetil. 2023; 164(32): 1247-1255.

SDPS-09 MIXED RESPONSE OF BRAIN METASTASES TREATED WITH OSIMERTINIB PREDICTS INFERIOR SURVIVAL OUTCOMES: AN ARTIFICIAL INTELLIGENCE-BASED LESION-LEVEL ASSESSMENT FOR CRANIAL CONTROL OF EGFRMUTANT NONSMALL CELL LUNG CANCER

Abstract Osimertinib has been found to be effective for intracranial control in patients with metastatic EGFR-mutant non-small cell lung cancer (NSCLC). However, the lesion-level response of brain metastases to osimertinib has not been thoroughly evaluated. This retrospective study included 73 patients with EGFR-mutant NSCLC and brain metastases who were treated with osimertinib at a single institution from 2016 to 2021. Patients with the leptomeningeal disease were excluded. The study used an FDA-approved brain tumor management artificial intelligence (AI) platform, VBrain, to identify, track, and measure brain metastases on the baseline and follow-up MRI brain scans. Mixed response (MiR) was defined as the occurrence of progressive or new lesions along with synchronous responsive shrinking intracranial lesions at the first follow-up scan. K-means grouping was used to partition patients into two clusters according to their response heterogeneity. With a median follow-up of 23.8 months, a high MiR score (higher than 103%, n=25) was associated with worse cranial-progression-free survival (3.2 vs. 17.9 months, p&amp;lt;0.0001) and significantly inferior overall survival (12.4 vs. 30.1 months, HR=2.35, p=0.016). This poses a similar negative impact on the survivals of 18 patients with pure RANO-BM progression (HR=2.52, p=0.025). Eight patients had the highest MiR score (MiRmax), in whom synchronous new lesions and completely responsive tumors were observed. In a multivariate Cox proportional-hazards regression involving performance status, extracranial failure, tumor volume, lesion number, and RANO-BM classification as variables, MiRmax remained an independent prognosticator for inferior survival (HR=5.20, 95%CI; 2.21–12.23, p=0.002). Our study demonstrates that MiR in brain metastases from EGFR-mutant NSCLC treated with osimertinib is associated with inferior survival outcomes and a higher risk of local progression. Lesion-level response assessment using AI may provide important prognostic information and aid in treatment decision-making for these patients.

Molecular Imaging of Glial Tumors: Established and Emerging Tracers

AbstractVarious positron emission tomography (PET) tracers have been developed and extensively studied in the field of neuro-oncology imaging. In the management of brain tumors, accurate delineation of tumor extent, assessment of treatment response, and detection of early recurrence are the most important factors. At present, conventional anatomical imaging paired with amino acid tracer PET imaging is the recommended imaging modality for glial tumor evaluation. Newer PET tracers targeting various structures in the tumor microenvironment have been extensively studied. This review summarizes the established and emerging PET tracers having potential impact on neuro-oncology practice.

Magnetic resonance imaging findings of intracranial extraventricular ependymoma: A retrospective multi-center cohort study of 114 cases.

Intracranial extraventricular ependymoma (IEE) is an ependymoma located in the brain parenchyma outside the ventricles. IEE has overlapping clinical and imaging characteristics with glioblastoma multiforme (GBM) but different treatment strategy and prognosis. Therefore, an accurate preoperative diagnosis is necessary for optimizing therapy for IEE. A retrospective multicenter cohort of IEE and GBM was identified. MR imaging characteristics assessed with the Visually Accessible Rembrandt Images (VASARI) feature set and clinicopathological findings were recorded. Independent predictors for IEE were identified using multivariate logistic regression, which was used to construct a diagnostic score for differentiating IEE from GBM. Compared to GBM, IEE tended to occur in younger patients. Multivariate logistic regression analysis identified seven independent predictors for IEE. Among them, 3 predictors including tumor necrosis rate (F7), age, and tumor-enhancing margin thickness (F11), demonstrated higher diagnostic performance with an Area Under Curve (AUC) of more than 70% in distinguishing IEE from GBM. The AUC was 0.85, 0.78, and 0.70, with sensitivity of 92.98%, 72.81%, and 96.49%, and specificity of 65.50%, 73.64%, and 43.41%, for F7, age, and F11, respectively. We identified specific MR imaging features such as tumor necrosis and thickness of enhancing tumor margins that could help to differentiate IEE from GBM. Our study results should be helpful to assist in diagnosis and clinical management of this rare brain tumor.

Clinico-epidemiological Profile of Primary Brain Tumours in North-Eastern Region of India:A Retrospective Single Institution Study

Background: Brain tumours are mixed group of neoplasms originating from the intracranial tissues. The two basic types of brain tumours are primary and metastatic tumours. Very little is known about the epidemiology of primary brain tumours in the North-Eastern region of India. We carried out a 5-year retrospective study on the epidemiology of the primary brain tumour treated in our hospital.Aim: To study the clinico-epidemiological patterns of brain tumour in a tertiary care center in North-Eastern region of India. Materials and Methods: A retrospective epidemiological approach has been used. The records of patients registered in our hospital from 2017-2022 diagnosed as primary brain tumours have been selected. Data regarding age,sex,site of the tumour, histology, geographical distribution and treatment delivered have been collected. Results: Out of a total of 100 patients studied, males (68%) outnumbered females (32%) with a male:female ratio of 2.1:1. Frequency of brain tumours was found to be higher in the age group 31-40 years i.e. 23% compared to age groups 21-30 years and 41-50 years which were 18% and 15% respectively. Mean age was 38.23 years with ages ranging from 4 to 73 years. The most common presenting symptom was headache (53%), followed by vomiting (28%).The most common anatomical site was found to be cerebrum (81%), followed by ventricular and periventricular regions (6%). Supratentorial tumours (91%) were predominant over infratentorial tumours (9%). Histologically, the most common variety was found to be Glioblastoma Multiforme(30%) followed by Grade II Astrocytoma (15%) and GradeIII Astrocytoma (15%). Patients were mostly seen to be belonging to Lower Assam region (46%) . Among all the patients in the study, surgery was done for 90% of patients while 10% did not undergo surgery. 61% of the patients took radiotherapy and chemotherapy, 22% took radiotherapy alone, 7% defaulted treatment(drop outs) and 10% didn’t turn up for treatment. All patients received a radiation dose of 54-60 Gy. A total of 41 patients took adjuvant chemotherapy with Temozolomide. Conclusion: Glioblastoma Multiforme and Astrocytoma are the most common brain tumours in our study. Multimodality management including surgery, radiotherapy and chemotherapy is the cornerstone in the management of brain tumours.

Surgical Management of Brain Tumors with Focused Ultrasound

Focused ultrasound is a novel technique for the treatment of aggressive brain tumors that uses both mechanical and thermal mechanisms. This non-invasive technique can allow for both the thermal ablation of inoperable tumors and the delivery of chemotherapy and immunotherapy while minimizing the risk of infection and shortening the time to recovery. With recent advances, focused ultrasound has been increasingly effective for larger tumors without the need for a craniotomy and can be used with minimal surrounding soft tissue damage. Treatment efficacy is dependent on multiple variables, including blood-brain barrier permeability, patient anatomical features, and tumor-specific features. Currently, many clinical trials are currently underway for the treatment of non-neoplastic cranial pathologies and other non-cranial malignancies. In this article, we review the current state of surgical management of brain tumors using focused ultrasound.

Navigating the challenges of neuro-oncology in Africa: addressing diagnostic and treatment barriers in the region: a correspondence

Navigating the challenges of neuro-oncology in Africa: addressing diagnostic and treatment barriers in the region: a correspondence

Coexistence of Cerebellopontine Angle Tumor and Frontal Convexity Meningioma at Distinct Location – A Rare Case Report and Review of Literature

The perioperative management of brain tumors can be significantly impacted by the presence of another intracranial tumor at a distinct location. We report a rare case of an adult who developed two primary brain tumors, a frontal convexity meningioma and a cerebellopontine angle (CPA) tumor at anatomically disparate locations. In our patient, it was unambiguously decided to address the CPA tumor first as it had led to multiple cranial nerve palsies and obstructive hydrocephalus. The relevant literature helped us better extrapolate the patient presentation and management of this disastrous presentation swiftly.

Symptom management in adult brain tumours: A literature review.

To review the literature related to symptom management, clinical significance and related theoretical framework systems in adult patients with brain tumours. As understanding of symptoms or symptom clusters and underlying biologic mechanisms has grown, it is apparent that symptom science is moving forward. Although some progress has been made in the symptom science of solid tumours such as breast and lung neoplasms, insufficient attention has been paid to symptom management for patients suffering from brain tumours. Further research is needed to achieve effective symptom management for these patients. A literature review with a systematic search of symptom management in adult brain tumours. Electronic data bases were searched to obtain relevant published literature on symptom management in adults with brain tumours. This was then analysed and a synthesis of relevant findings is presented. Four significant general themes relating to symptom management of brain tumours in adults were identified: (1) The potential theoretical foundation related to symptom management was revealed. (2) Widely accepted validated scales or questionnaires for the assessment of single symptoms or symptom clusters were recommended. (3) Several symptom clusters and the underlying biologic mechanisms have been reported. (4) Specific symptom interventions for adults with brain tumours were collected and classified as evidence-based or insufficient evidence. There are still many challenges in the effective management of symptoms in adults with brain tumours. The guiding role of theoretical frameworks or models related to symptom management should be utilized in future research. Using the concept of symptom clustering for research into symptoms found in patients with brain tumours, exploring common biological mechanisms for specific symptom clusters and making full use of modern big data resources to build a strong evidence base for an effective intervention or management program may inform the management of symptoms among these patients leading to better results. This is a literature review. The ultimate goal is obviously not only improving the survival rate of patients with brain tumours, but also enhancing their quality of life. Several important findings from our review include the theoretical foundations, validated assessment tools, the assessment of symptom clusters and the underlying biologic mechanism, and the identification of the evidence base for symptom interventions. These are of relevance for managers, researchers and practitioners and may function as a reference to help the effective symptom management for adults with brain tumours.

Imaging Cancer in Neuroradiology

Neuroimaging plays a pivotal role in the diagnosis, management, and prognostication of brain tumors. Recently, the World Health Organization published the fifth edition of the WHO Classification of Tumors of the Central Nervous System (CNS5), which places greater emphasis on tumor genetics and molecular markers to complement the existing histological and immunohistochemical approaches. Recent advances in computational power allowed modern neuro-oncological imaging to move from a strictly morphology-based discipline to advanced neuroimaging techniques with quantifiable tissue characteristics such as tumor cellularity, microstructural organization, hemodynamic, functional, and metabolic features, providing more precise tumor diagnosis and management. The aim of this review is to highlight the key imaging features of the recently published CNS5, outlining the current imaging standards and summarizing the latest advances in neuro-oncological imaging techniques and their role in complementing traditional brain tumor imaging and management.

102 AI-Based Molecular Classification of Diffuse Gliomas using Rapid, Label-Free Optical Imaging

Molecular classification has transformed the management of brain tumors by enabling more accurate prognostication and personalized treatment. Access to timely molecular diagnostic testing for brain tumor patients is limited, complicating surgical and adjuvant treatment and obstructing clinical trial enrollment. By combining stimulated Raman histology (SRH), a rapid, label-free, non-consumptive, optical imaging method, and deep learning-based image classification, we are able to predict the molecular genetic features used by the World Health Organization (WHO) to define the adult-type diffuse glioma taxonomy, including IDH-1/2, 1p19q-codeletion, and ATRX loss. We developed a multimodal deep neural network training strategy that uses both SRH images and large-scale, public diffuse glioma genomic data (i.e. TCGA, CGGA, etc.) in order to achieve optimal molecular classification performance. One institution was used for model training (University of Michigan) and four institutions (NYU, UCSF, Medical University of Vienna, and University Hospital Cologne) were included for patient enrollment in the prospective testing cohort. Using our system, called DeepGlioma, we achieved an average molecular genetic classification accuracy of 93.2% and identified the correct diffuse glioma molecular subgroup with 91.5% accuracy within 2 minutes in the operating room. DeepGlioma outperformed conventional IDH1-R132H immunohistochemistry (94.2% versus 91.4% accuracy) as a first-line molecular diagnostic screening method for diffuse gliomas and can detect canonical and non-canonical IDH mutations. Our results demonstrate how artificial intelligence and optical histology can be used to provide a rapid and scalable alternative to wet lab methods for the molecular diagnosis of brain tumor patients during surgery.

Artificial-intelligence-based molecular classification of diffuse gliomas using rapid, label-free optical imaging.

Molecular classification has transformed the management of brain tumors by enabling more accurate prognostication and personalized treatment. However, timely molecular diagnostic testing for patients with brain tumors is limited, complicating surgical and adjuvant treatment and obstructing clinical trial enrollment. In this study, we developed DeepGlioma, a rapid (<90 seconds), artificial-intelligence-based diagnostic screening system to streamline the molecular diagnosis of diffuse gliomas. DeepGlioma is trained using a multimodal dataset that includes stimulated Raman histology (SRH); a rapid, label-free, non-consumptive, optical imaging method; and large-scale, public genomic data. In a prospective, multicenter, international testing cohort of patients with diffuse glioma (n = 153) who underwent real-time SRH imaging, we demonstrate that DeepGlioma can predict the molecular alterations used by the World Health Organization to define the adult-type diffuse glioma taxonomy (IDH mutation, 1p19q co-deletion and ATRX mutation), achieving a mean molecular classification accuracy of 93.3 ± 1.6%. Our results represent how artificial intelligence and optical histology can be used to provide a rapid and scalable adjunct to wet lab methods for the molecular screening of patients with diffuse glioma.

A Review on Brain Tumour, Etiology and Treatment

Brain tumors are common, requiring general medical providers to have a basic understanding of their diagnosis and management. The most prevalent brain tumors are intracranial metastases from systemic cancers, meningiomas, and gliomas, specifically, glioblastoma. Central nervous system metastases may occur anywhere along the neuroaxis, and require complex multidisciplinary care with neurosurgery, radiation oncology, and medical oncology. Meningiomas are tumors of the meninges, mostly benign and often managed by surgical resection, with radiation therapy and chemotherapy reserved for high-risk or refractory disease. Glioblastoma is the most common and aggressive malignant primary brain tumor, with a limited response to standard-of-care concurrent chemoradiation. This review addresses the specific contributions of nuclear medicine techniques, and especially positron emission tomography (PET), for diagnosis and management of brain tumors. F-Fluorodeoxyglucose PET has particular strengths in predicting prognosis and differentiating cerebral lymphoma from nonmalignant lesions. Amino acid tracers including C-methionine, F-fluoroethyltyrosine, and F-L-3,4-dihydroxyphenylalanine provide high sensitivity, which is most useful for detecting recurrent or residual gliomas, including most low-grade gliomas. They also play an increasing role for planning and monitoring of therapy. F-fluorothymidine can only be used in tumors with absent or broken blood–brain barrier and has potential for tumor grading and monitoring of therapy. Ligands for somatostatin receptors are of particular interest in pituitary adenomas and meningiomas. Tracers to image neovascularization, hypoxia, and phospholipid synthesis are under investigation for potential clinical use.